prefetch the next packet data address in advance in forwarding loop for performance improvement.
Signed-off-by: Jerin Jacob <jerin.jacob at caviumnetworks.com> --- V2: Extend the packet data prefetch logic to other similar forwarding modes like macfwd, macfwd-retry, csumonly, icmpecho as suggested by Pablo http://dpdk.org/dev/patchwork/patch/12330/ --- app/test-pmd/csumonly.c | 3 +++ app/test-pmd/icmpecho.c | 3 +++ app/test-pmd/macfwd-retry.c | 3 +++ app/test-pmd/macfwd.c | 3 +++ app/test-pmd/macswap.c | 3 +++ 5 files changed, 15 insertions(+) diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c index 7e4f662..1d6cda1 100644 --- a/app/test-pmd/csumonly.c +++ b/app/test-pmd/csumonly.c @@ -676,6 +676,9 @@ pkt_burst_checksum_forward(struct fwd_stream *fs) info.tso_segsz = txp->tso_segsz; for (i = 0; i < nb_rx; i++) { + if (likely(i < nb_rx - 1)) + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1], + void *)); ol_flags = 0; info.is_tunnel = 0; diff --git a/app/test-pmd/icmpecho.c b/app/test-pmd/icmpecho.c index e510f9b..ed6e924 100644 --- a/app/test-pmd/icmpecho.c +++ b/app/test-pmd/icmpecho.c @@ -346,6 +346,9 @@ reply_to_icmp_echo_rqsts(struct fwd_stream *fs) fs->rx_packets += nb_rx; nb_replies = 0; for (i = 0; i < nb_rx; i++) { + if (likely(i < nb_rx - 1)) + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1], + void *)); pkt = pkts_burst[i]; eth_h = rte_pktmbuf_mtod(pkt, struct ether_hdr *); eth_type = RTE_BE_TO_CPU_16(eth_h->ether_type); diff --git a/app/test-pmd/macfwd-retry.c b/app/test-pmd/macfwd-retry.c index 3a96b3d..d8cd069 100644 --- a/app/test-pmd/macfwd-retry.c +++ b/app/test-pmd/macfwd-retry.c @@ -117,6 +117,9 @@ pkt_burst_mac_retry_forward(struct fwd_stream *fs) #endif fs->rx_packets += nb_rx; for (i = 0; i < nb_rx; i++) { + if (likely(i < nb_rx - 1)) + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1], + void *)); mb = pkts_burst[i]; eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *); ether_addr_copy(&peer_eth_addrs[fs->peer_addr], diff --git a/app/test-pmd/macfwd.c b/app/test-pmd/macfwd.c index 3b7fffb..07a399a 100644 --- a/app/test-pmd/macfwd.c +++ b/app/test-pmd/macfwd.c @@ -113,6 +113,9 @@ pkt_burst_mac_forward(struct fwd_stream *fs) if (txp->tx_ol_flags & TESTPMD_TX_OFFLOAD_INSERT_QINQ) ol_flags |= PKT_TX_QINQ_PKT; for (i = 0; i < nb_rx; i++) { + if (likely(i < nb_rx - 1)) + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1], + void *)); mb = pkts_burst[i]; eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *); ether_addr_copy(&peer_eth_addrs[fs->peer_addr], diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c index 154889d..c10f4b5 100644 --- a/app/test-pmd/macswap.c +++ b/app/test-pmd/macswap.c @@ -113,6 +113,9 @@ pkt_burst_mac_swap(struct fwd_stream *fs) if (txp->tx_ol_flags & TESTPMD_TX_OFFLOAD_INSERT_QINQ) ol_flags |= PKT_TX_QINQ_PKT; for (i = 0; i < nb_rx; i++) { + if (likely(i < nb_rx - 1)) + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1], + void *)); mb = pkts_burst[i]; eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *); -- 2.1.0
